This Article 
 Bibliographic References 
 Add to: 
A DRAM/SRAM Memory Scheme for Fast Packet Buffers
May 2006 (vol. 55 no. 5)
pp. 588-602
We address the design of high-speed packet buffers for Internet routers. We use a general DRAM/SRAM architecture for which previous proposals can be seen as particular cases. For this architecture, large SRAMs are needed to sustain high line rates and a large number of interfaces. A novel algorithm for DRAM bank allocation is presented that reduces the SRAM size requirements of previously proposed schemes by almost an order of magnitude, without having memory fragmentation problems. A technological evaluation shows that our design can support thousands of queues for line rates up to 160 Gbps.

[1] Altera, “Linear Feedback Shift Register Megafunction,” Dec. 2001, .
[2] G. Appenzeller, I. Keslassy, and N. McKeown, “Sizing Router Buffers,” ACM SIGCOMM, Aug. 2004.
[3] S.B. Murkherjee, D. Danerjee, and A. Murkherjee, “A Generalized Processor Sharing Approach to Flow Control in Integrated Services Networks: The Multiple-Node CAS,” IEEE/ACM Trans. Networking, vol. 4, pp. 684-696, 1996.
[4] V. Bollapragada, R. White, and C. Murphy, Inside Cisco IOS Software Architecture. Cisco Press, July 2000.
[5] C. Chang, D. Lee, and Y. Jou, “Load Balanced Birkhoff-von Neumann Switches, Part I: One-Stage Buffering,” Computer Comm., vol. 25, pp. 661-622, 2002.
[6] Y. Chen and J. Turner, “WDM Burst Switching For Petabit Capacity Routers,” Proc. Military Comm. Conf. (MILCOM), pp. 968-973 1999.
[7] Cisco, “Cisco Carrier Router System,” index.html, 2005.
[8] J. Corbal, R. Espasa, and M. Valero, “Command-Vector Memory System,” Proc. IEEE Parallel Architectures and Compilation Techniques (PACT '98), Nov. 1998.
[9] C. Crisp, “Provisioning Internet Backbone Networks to Support Latency Sensitive Applications,” PhD dissertation, Stanford Univ., June 2002.
[10] R. Crisp, “Direct Rambus Technology: The New Main Memory Standard,” IEEE Micro, vol. 7, pp. 18-28, Nov./Dec. 1997.
[11] A. Dhamdhere, H. Jiang, and C. Dovrolis, “Buffer Sizing for Congested Internet Links,” Proc. IEEE Infocomm, Mar. 2005.
[12] M.D.K. Hunter and I. Andonovic, “Buffering in Optical Packet Switches,” J. Lightwave Technology, vol. 16, pp. 2081-2094, Dec. 1998.
[13] W. Eatherton, “Router/Switch Architecture with Networking Specific Memories,” Proc. Memory, Storage, and Serial Interface Technology Conf. (MemCon 2002), Oct. 2002.
[14] Fujitsu, “256M bit Double Data Rate FCRAM, MB81N26847B/261647B-50/-55/-60 data sheet,” http:/, 2004.
[15] J. Gabriagues and J. Jacob, “OASIS: A High-Speed Photonic ATM Switch— Results and Perspectives,” Proc. 15th Int'l Switching Symp., pp. 457-461, Apr. 1995.
[16] J. García, L. Cerdà, and J. Corbal, “A Conflict-Free Memory Banking Architecture for Fast Packet Buffers,” Technical Report UPC-DAC-2002-50, Politechnic Univ. of Catalonia, July 2002, 2002.
[17] J. García, J. Corbal, L. Cerdà, and M. Valero, “Design and Implementation of High-Performance Memory Systems for Future Packet Buffers,” Proc. MICRO '03, Dec. 2003.
[18] J. García, M. March, L. Cerdà, J. Corbal, and M. Valero, “On the Design of Hybrid DRAM/SRAM Memory Schemes for Fast Packet Buffers,” Proc. IEEE High Performance Switching and Routing (HPSR), pp. 15-19, Apr. 2004.
[19] G. Iannaccone, M. May, and C. Diot, “Aggregate Traffic Performance with Active Queue Management and Drop from Tail,” SIGCOMM, vol. 37, pp. 277-306, 2001.
[20] G. Glykopoulos, “Design and Implementation of a 1.2 Gbit/s ATM Cell Buffer Using a Synchronous DRAM Chip,” Technical Report 221, ICS-FORTH, July 1998, .
[21] C. Guillermot, “Transparent Optical Packet Switching: The European ACTS KEOPS Project Approach,” J. Lightwave Technology, vol. 16, no. 12, pp. 2117-2133, Dec. 1998.
[22] J. Hasan, S. Chandra, and T. Vijaykumar, “Efficient Use of Memory Bandwidth to Improve Network Processor Throughput,” Proc. 30th Ann. Int'l Symp. Computer Architecture (ISCA), June 2003.
[23] Hitachi, “Hitachi 166 Mhz SDRAM,” Hitachi HM5257XXb series, 2000, htm .
[24] D. Hunter, “WASPNET: A Wavelength Switched Packet Network,” IEEE Comm. Magazine, pp. 120-129, Mar. 1999.
[25] D. Hunter, W. Cornwall, T. Gilfedder, A. Franzen, and I. Andonovic, “SLOB: A Switch with Large Optical Buffers for Packet Switching,” IEEE/OSA J. Lightwave Technology, vol. 16, no. 10, Oct. 1998.
[26] A.F.I. Chlamtac and T. Zang, “Lightpah Routing in Large WDM Networks,” IEEE J. Selected Areas in Comm., vol. 14, pp. 909-913, June 1996.
[27] D. Harper and J. Jump, “Performance Evaluation of Vector Accesses in Parallel Memories Using a Skewed Storage Scheme,” Proc. 13th Int'l Symp. Computer Architecture (ISCA), pp. 324-328, 1986.
[28] Infineon Tech nologies, “RLDRAM. High Density, High-Bandwidth Memory for Networking Applications,” http:/www., 2004.
[29] S. Iyer, R. Kompella, and N. McKeown, “Designing Buffers for Router Line Cards,” Technical Report TR02-HPNG-031001, Stanford Univ., Nov. 2002, .
[30] Juniper, “Juniper T640,”, 2005.
[31] J.S.K. Dolzer, C. Gauger, and S. Bodamer, “Evaluation of Reservation Mechanisms for Optical Burst Switching,” AEU Int'l J. Electronics and Comm., vol. 55, no. 1, 2001.
[32] M. Karol, “Shared-Memory Optical Packet (ATM) Switch,” Multigigabit Fiber Comm. Systems, vol. 2024, pp. 212-222, 1993.
[33] I. Keslassy, S. Chuang, and N. Mckeown, “Architectures and Algorithms for a Load-Balanced Switch,” Technical Report TR03-HPNG-061501, Stanford Univ., June 2003.
[34] I. Keslassy, S. Chuang, and N. McKeown, “A Load-Balanced Switch with an Arbitrary Number of Linecards,” Proc. IEEE Infocom, Mar. 2004.
[35] I. Keslassy, S. Chuang, K. Yuu, D. Miller, M. Horowitz, O. Solgaard, and N. McKeown, “Scaling Internet Routers Using Optics,” ACM SIGCOMM, Aug. 2003.
[36] C. Minkenberg, R. Luijten, W. Denzel, and M. Gusat, “Current Issues in Packet Switch Design,” Proc. HotNets-I, Oct. 2002.
[37] A. Nikologiannis and M. Katevenis, “Efficient Per-Flow Queueing in DRAM at OC-192 Line Rate Using Out of Order Execution Techniques,” Proc. IEEE Int'l Conf. Comm., June 2001.
[38] C. Quiao and M. Yoo, “Optical Burst Switching (OBS): A New Paradigm for an Optical Internet,” J. High Speed Networks, vol. 8, no. 1, pp. 69-84, 1999.
[39] R. Ramaswami and K.N. Sirvajan, Optical Networks. San Mateo, Calif.: Morgan Kaufman, 1990.
[40] B. Rau, M. Schlansker, and D. Yen, “The Cydra 5 Stride-Insensitive Memory System,” Proc. Int'l Conf Parallel Processing, pp. 242-246, 1989.
[41] P. Shivakumar and N. Jouppi, “Cacti 3.0: An Integrated Cache Timing, Power and Area Model,” technical report, Compaq Computer Corp., Aug. 2001, CACTI.html.
[42] R. Spanke, “Architectures for Large Nonblocking Optical Space Switches,” IEEE J. Quantum Electronics, vol. 22, no. 6, pp. 964-967, June 1986.
[43] Y. Tamir and G. Frazier, “High-Performance Multi-Queue Buffers for VLSI Communication Switches,” Proc. 15th Int'l Symp. Computer Architecture (ISCA), pp. 343-354, May 1988.
[44] S. Tariq, M. Dhodhi, J. Palais, and R. Ahmed, “Next Generation DWDM Networks: Demands, Capabilities and Limitations,” Proc. Canadian Conf. Electrical and Computer Eng., pp. 1003-1007, 2000.
[45] J. Turner, “Terabit Burst Switching,” J. High Speed Networks, vol. 8, pp. 3-6, 1999.
[46] M. Valero, T. Lang, J. LLaberia, M. Peiron, E. Ayguade, and J. Navarro, “Increasing the Number of Strides for Conflict-Free Vector Access,” Proc. 19th Int'l Symp. Computer Architecture (ISCA), pp. 372-381, May 1992.
[47] M. Valero, T. Lang, M. Peiron, and E. Ayguade, “Increasing the Number of Conflict-Free Vector Access,” IEEE Trans. Computers, vol. 44, no. 5, pp. 634-646, May 1995.
[48] D. Wischik and N. McKeown, “Part I: Buffer Sizes for Core Routers,” Computer Comm. Rev., vol. 35, no. 3, pp. 75-78, 2005.
[49] Xilinx, “Pseudo Random Number Generator,” Dec. 2001, .
[50] C.Q.Y. Chen and X. Yu, “Optical Burst Switching (OBS): A New Area in Optical Networking Research,” IEEE Network Magazine, vol. 18, no. 4, pp. 16-23, 2004.
[51] W. Zhong and R. Tucker, “Wavelength Routing-Based Photonic Packet Buffers and Their Applications in Photonic Packet Switching Systems,” J. Lightwave Technology, vol. 16, no. 10, pp. 1737-45, Oct. 1998.

Index Terms:
Router architecture, packet buffers, high-performance memory systems, storage schemes.
Jorge Garc?a-Vidal, Maribel March, Lloren? Cerd?, Jes? Corbal, Mateo Valero, "A DRAM/SRAM Memory Scheme for Fast Packet Buffers," IEEE Transactions on Computers, vol. 55, no. 5, pp. 588-602, May 2006, doi:10.1109/TC.2006.63
Usage of this product signifies your acceptance of the Terms of Use.